app.py

import gradio as gr
from moviepy.editor import *
from share_btn import community_icon_html, loading_icon_html, share_js

caption = gr.Blocks.load(name="spaces/SRDdev/Image-Caption")
audio_gen = gr.Blocks.load(name="spaces/haoheliu/audioldm-text-to-audio-generation")

def infer(image_input):
    cap = caption(image_input, fn_index=0)
    sound = audio_gen(cap, 5, 2.5, 45, 3, fn_index=0)
    FILETOCONVERT = AudioFileClip(sound)
    FILETOCONVERT.write_audiofile("audio.wav")
    FILETOCONVERT.close()
    return gr.Textbox.update(value=cap, visible=True), "audio.wav", gr.Group.update(visible=True)

title = """
    <div style="text-align: center; max-width: 700px; margin: 0 auto;">
        <div
        style="
            display: inline-flex;
            align-items: center;
            gap: 0.8rem;
            font-size: 1.75rem;
        "
        >
        <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
            Image to Sound Effect
        </h1>
        </div>
        <p style="margin-bottom: 10px; font-size: 94%">
        Convert an image to corresponding sound effect through gpt2 image captioning & AudioLDM
        </p>
    </div>
"""

article = """
    
    <div class="footer">
        <p>
         
        Follow <a href="https://twitter.com/fffiloni" target="_blank">Sylvain Filoni</a> for future updates 🤗
        </p>
    </div>    
"""

with gr.Blocks(css="style.css") as demo:
    with gr.Column(elem_id="col-container"):
        
        gr.HTML(title)
    
        input_img = gr.Image(type="filepath", elem_id="input-img")
        caption_output = gr.Textbox(label="Caption", lines=1, visible=False, elem_id="text-caption")
        sound_output = gr.Audio(label="Result", elem_id="sound-output")
        
        generate = gr.Button("Generate SFX from Image")

        with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
            community_icon = gr.HTML(community_icon_html)
            loading_icon = gr.HTML(loading_icon_html)
            share_button = gr.Button("Share to community", elem_id="share-btn")

        gr.HTML(article)
        
    generate.click(infer, inputs=[input_img], outputs=[caption_output, sound_output, share_group], api_name="i2fx")
    share_button.click(None, [], [], _js=share_js)

demo.queue(max_size=32, concurrency_count=20).launch()